Generative Late-Interaction Embeddings For Visual Document Retrieval Paper • 2609.11808 • Published 14 days ago • 27
Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout Paper • 2609.09123 • Published 16 days ago • 55
Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs Paper • 2609.03820 • Published 21 days ago • 16
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning Paper • 2609.03430 • Published 21 days ago • 187
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM Paper • 2609.04098 • Published 21 days ago • 84
FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds Paper • 2608.01049 • Published Aug 2 • 13
The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads Paper • 2608.04570 • Published Aug 5 • 41
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks Paper • 2608.01964 • Published Aug 3 • 188
LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-Final-GGUF Image-Text-to-Text • 35B • Updated 5 days ago • 361k • 643